© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77579
    Prev
    Next
    INDEX
    Explanations

    encode, decrypt, session, tightening, production, Keynesian

    np_acts-logits-general · gemini-2.5-flash-lite

    ionize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ine
    0.49
     prov
    0.49
     aid
    0.46
     pill
    0.45
     she
    0.45
     rub
    0.45
    in
    0.45
    竖
    0.45
    ater
    0.44
     pox
    0.44
    POSITIVE LOGITS
     رفتار
    0.49
    NORMAL
    0.49
    ਵ
    0.49
    ੪
    0.48
    PLAY
    0.47
    mainan
    0.47
     ਜ਼
    0.47
    ຜະລິດຕ
    0.46
     रिटायर
    0.45
    日々
    0.45
    Activations Density 0.001%

    No Known Activations